Image-Text-to-Text
Transformers
Safetensors
English
Chinese
llava
vision-language
llm
lmm
conversational
Inference Endpoints
File size: 136 Bytes
48c6894
 
 
 
 
 
 
1
2
3
4
5
6
7
8
{
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 32001,
  "transformers_version": "4.36.2"
}